Multiple Electric Components Health-Aware Eco-Driving Strategy for Fuel Cell Hybrid Electric Vehicle Based on Soft Actor-Critic Algorithm

The eco-driving strategy based on deep reinforcement learning holds significant potential for achieving energy efficiency, longevity, and safety of fuel cell hybrid electric vehicle (FCHEV). This article proposes a health-aware eco-driving strategy for FCHEV based on the soft actor-critic (SAC) algorithm. Building upon health awareness of multiple electric components including power battery, fuel cell, and driving motor, this eco-driving strategy integrates energy management system (EMS) and adaptive cruise control (ACC) to comprehensively optimize vehicle performance. By incorporating health awareness into the eco-driving approach, this study aims to maximize the lifespan of electric components, enhance energy utilization efficiency, and ensure driving comfort and safety. SAC algorithm not only enhances optimization performance in complex nonlinear multiobjective optimization problems but also accommodates real-time control requirements under diverse driving conditions. The simulation results demonstrate that the proposed strategy achieves 0.41% reduction in H2 consumption and same level health maintenance of electric components compared with the dynamic programming (DP) benchmark of EMS, while maintaining the comfort within 6% of the gap but safer following performance compared with the intelligent driver model (IDM) benchmark of ACC. Moreover, the comparative experiments demonstrate that the effectiveness and adaptability of proposed eco driving strategy.

I. Introduction

Due to looming uncertainty around energy crisis, global warming, and pollution stemming from vehicular traffic, governments and automobile manufacturers are embarking on a transformative journey toward electric and eco-friendly transportation solutions [1], [2], [3]. With the continuous breakthroughs in fuel cell technology and the integration of Li-ion battery as supplementary power source, fuel cell hybrid electric vehicle (FCHEV) is gradually emerging as an effective solution for sustainable automobiles in the future, owing to their zero emissions, rapid refueling, extended range, and impressive durability [4]. Nonetheless, the application of FCHEV still confronts challenges related to FCS lifespan, high hydrogen cost, and expensive electric components [5]. In order to address these challenges, integrating internal and external optimization of FCHEV is considered as a feasible approach. On the one side, energy management system (EMS) is an energy-saving method for different power sources in FCHEV [6]. On the other side, advanced driver assistance system (ADAS) plays a critical role in safe and comfortable driving [7], and adaptive cruise control (ACC) is one of the most significant ADAS [8]. Therefore, eco-driving is a matching strategy realizing energy-saving, safe and efficient driving strategies in specific traffic scenarios, which consists of EMS for internal distributing energy and ACC for safe external following [9]. Based on the eco-driving strategy, health of FCEHV’s core electric components is also incorporated for their longevity. In this context, excellent following, longevity of components, energy efficiency, and sustainability of FCHEV can be ensured, aligning with the goals of a safe, secure, and sustainable future transportation system as outlined in Transportation 5.0 [10].